aicodeking/deepseek-stack

ds-sharpen

Restate the user's goal, make the task deeper rather than bigger, rewrite the prompt, and optionally attack the plan to find weak spots.

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/aicodeking/deepseek-stack --skill ds-sharpen

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

ds-sharpen

A sharper prompt saves more tokens than any loop. Fix the ask before doing the work.

Steps

  1. Restate, in your own words, what the user wants and the problem behind it. Keep it to three sentences. If you cannot, ask one question.
  2. Deepen the task. Answer briefly:
  • What would a top professional do here that the user did not ask for?
  • What raw material would they start from, instead of a summary?
  • What methods and tools would they use?
  • What outside check, not you or the user, would show the result is right? Name a command, test, metric or source.
  1. Rewrite the prompt to ask for exactly that. Keep it no bigger in scope. Leave choices that belong to the user open and list them.
  2. Optional stress test, when the plan is risky or the user asks. Spawn two or three subagents with fresh context and give each the plan and the goal. Ask each to break it and back every finding with a run: a failing test, a probe script, or real command output. Drop findings with no run behind them.
  3. Present the restatement, the rewritten prompt, open choices, and any surviving findings with their commands and output.

Stop when

  • The user accepts or edits the rewritten prompt.
  • Or the stress test returns. Do not loop it more than once without the user.

Rules

  • Deeper, not bigger. Do not add features.
  • Do not apply fixes from the stress test. Report them.
  • A finding without output is an opinion. Leave it out.
aus demselben Repository

Weitere Skills

Alle Skills